Ask Your Question
0

TensorFlow serving

asked 2019-05-19 04:16:54 -0600

Liyi gravatar image

updated 2019-05-19 04:20:01 -0600

When flow this blog(https://streamsets.com/blog/machine-learning-with-tensorflow-and-kafka-in-data-collector/), I got error like this on the Tenforflow processor:

 TENSOR_FLOW_02 - Error loading saved model : org.tensorflow.TensorFlowException: Op type not registered 'DivNoNan' in binary running on sdc-0. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) `tf.contrib.resampler` should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.

Anyone has got it worked for you? BR/Liyi

edit retag flag offensive close merge delete

1 Answer

Sort by ยป oldest newest most voted
0

answered 2019-06-04 11:49:15 -0600

iamontheinet gravatar image

updated 2019-06-04 11:49:55 -0600

Hi!

Please watch and vote on this (open) JIRA ticket -- https://issues.streamsets.com/browse/....

In the meantime, use TensorFlow version < 1.13 as a workaround.

As an example, you may refer to this code to see how to save/export TF models for them to be able to load in StreamSets TensorFlow Evaluator -- https://github.com/iamontheinet/datas...

Cheers, Dash

edit flag offensive delete link more
Login/Signup to Answer

Question Tools

1 follower

Stats

Asked: 2019-05-19 04:16:54 -0600

Seen: 165 times

Last updated: Jun 04